2 papers
cs.LG2026
GDRO: Group-level Reward Post-training Suitable for Diffusion Models
Yiyang Wang, Xi Chen, Xiaogang Xu +2
Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards success…
cs.CV2025
DiffCamera: Arbitrary Refocusing on Images
Yiyang Wang, Xi Chen, Xiaogang Xu +2
The depth-of-field (DoF) effect, which introduces aesthetically pleasing blur, enhances photographic quality but is fixed and difficult to modify once the image has been created. T…